Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016
New Posts  All Forums:Forum Nav:

[TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016 - Page 6

post #51 of 724
I'm so ready for a new GPU! I hope I can get a GPU that is 30-50% faster than my GTX 970 for around £280-350!
post #52 of 724
Quote:
Originally Posted by TopicClocker View Post

I'm so ready for a new GPU! I hope I can get a GPU that is 30-50% faster than my GTX 970 for around £280-350!


You definitely should. If they don't make a GPU for 350 pound sterling that is atleast 50% faster than the GTX 970 then something is definitely wrong with the industry and we all might just give up PC gaming.
TBH the GTX 970 is relatively speaking considering what year we have and how much time has passed since the 7970 not a really good GPU.
current rig
(4 items)
 
  
CPUGraphicsGraphicsKeyboard
2500k R9 290X Tri-X GTX 680 Filco Majestouch 2 Brown Ninja 
  hide details  
Reply
current rig
(4 items)
 
  
CPUGraphicsGraphicsKeyboard
2500k R9 290X Tri-X GTX 680 Filco Majestouch 2 Brown Ninja 
  hide details  
Reply
post #53 of 724
This isn't news...

HBM2 GPU's won't show up until the Q3, this has been known for quite some time. This does not mean that Pascal and Polaris GPU's won't show up before then as the mid grade cards (R9 490, GTX 1080, etc.) won't be using HBM2, but GDDR5X. Those cards will release in the next month or two. Then around Q3, the 1080ti, Titan P (still going with that as it's title), and the successor to the Fury and Fury X all sporting HBM2 will arrive.

I would expect the Titan P to be the first to show up around computex, followed shortly by the AMD cards and finally the 1080ti showing up in time for the holidays.
post #54 of 724
GTX 1070 here I come! Hoping I can get at least 3x the performance of my GTX 670
Neutrino
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7 6700K Asus Z170I PRO GAMING Gigabyte GTX 1070 Mini ITX Corsair 16GB (2 x 8GB) DDR4-3200MHz 
Hard DriveCoolingCoolingOS
Crucial MX300 750GB Scythe Big Shuriken 2 rev. B Cryorig XT140 fan Windows 10 Pro 
KeyboardPowerCaseMouse
Topre Realforce 87u 55g Corsair SF450 Lazer3D LZ7 Logitech G303 
Mouse PadAudio
Steelseries 4HD Audio Technica ATH-M50 
  hide details  
Reply
Neutrino
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7 6700K Asus Z170I PRO GAMING Gigabyte GTX 1070 Mini ITX Corsair 16GB (2 x 8GB) DDR4-3200MHz 
Hard DriveCoolingCoolingOS
Crucial MX300 750GB Scythe Big Shuriken 2 rev. B Cryorig XT140 fan Windows 10 Pro 
KeyboardPowerCaseMouse
Topre Realforce 87u 55g Corsair SF450 Lazer3D LZ7 Logitech G303 
Mouse PadAudio
Steelseries 4HD Audio Technica ATH-M50 
  hide details  
Reply
post #55 of 724
Quote:
Originally Posted by prjindigo View Post

Oh, the 970 accessing 3.8gb of the 3.5gb of ram it was given was pretty much a dead give-away in the end.

No clue what you're trying to say here.

Quote:
You do understand the term "array" right? That data takes a shape in memory and there are efficient and inefficient ways to handle said data?

You do understand what I said in my post, right? There are twelve 32-bit wide memory channels on the 980 Ti mapped to twelve 512 MB memory chips and a fully intact 3 MBs of L2 cache. It's a uniform 1:1 ratio which means the 980 Ti accesses all of its 6 GBs of VRAM at full speed with no XOR contention issues like the 970.

Quote:
That the whole point of HBM/HBM2 is changing the way the data is handled into a symmetrical form on the card? That this results in nV needing to change away from their 384 bus system...

No, the whole point of HBM is to continue increasing bandwidth while simultaneously decreasing power consumption. It has the added benefits of increased memory density, reduced latency, and reduced PCB complexity. There is nothing fundamentally wrong with GDDR5's ability to handle data. If there was, GDDR5 would be a fundamentally broken memory technology that would have never gained traction and it would mean all GDDR5-equipped cards (both AMD and Nvidia) have memory issues.

As to you're singling out of Nvidia's 384-bit memory buses, there's nothing asymmetrical about them. I've addressed this already. 1:1 mapping of memory chips to memory channels and all. Considering your original post on the subject mistakenly stated that 8 GBs would be the proper fit for a 384-bit bus, despite chips of the size necessary to do so not existing, it's clear that you don't understand GPU memory subsystems. Please, read up on the subject before insisting on false information.
Edited by Serandur - 1/22/16 at 10:22pm
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
Ice-nine
(17 items)
 
  
CPUMotherboardGraphicsRAM
i7-6700K Asus Z170-DELUXE Gigabyte G1 GTX 980 Ti Corsair Vengeance LPX DDR4 3000 
Hard DriveHard DriveOptical DriveCooling
Samsung 850 Evo 500 GB Seagate Barracuda 7200 RPM 2 TB Asus DVD Drive DRW-24B1ST/BLK/B/AS Phanteks PH-TC14PE 
OSMonitorKeyboardPower
Windows 8.1 Pro AOC Q2770PQU Corsair K95 RGB - Cherry MX Blue EVGA Supernova G2 750W 
CaseMouseMouse PadAudio
NZXT Phantom 410 Gunmetal Edition Logitech G502 Proteus Core Razer Goliathus Speed Edition Small Cyber Acoustics Satellite CA-3602 
Audio
Oppo PM-3 Closed Back Planar Magnetic Headphones 
  hide details  
Reply
post #56 of 724
Quote:
Originally Posted by Serandur View Post

There is nothing fundamentally wrong with GDDR5's ability to handle data. If there was, GDDR5 would be a fundamentally broken memory technology that would have never gained traction and it would mean all GDDR5-equipped cards (both AMD and Nvidia) have memory issues.
Quite the slippery slope argument. GDDR5 is just too constrained by the mw/gbps. 42% transmission power reduction from GDDR5 to HBM is a lot(72%) of extra I/O power efficiency.
The Machine
(14 items)
 
Nexus 7 2013
(11 items)
 
 
CPUMotherboardGraphicsRAM
A10 6800K Asus F2A85-V MSI 6870 Hawx, VTX3D 5770, AMD HD6950(RIP), Sap... G.skill Ripjaws PC12800 6-8-6-24 
Hard DriveOptical DriveOSMonitor
Seagate 7200.5 1TB NEC 3540 Dvd-Rom Windows 7 x32 Ultimate Samsung P2350 23" 1080p 
PowerCaseMouseAudio
Seasonic s12-600w CoolerMaster Centurion 5 Logitech G600 Auzen X-Fi Raider 
CPUMotherboardGraphicsRAM
Quad Krait 300 at 1.5Ghz Qualcomm APQ8064-1AA SOC Adreno 320 at 400mhz 2GB DDR3L-1600 
Hard DriveOSMonitorKeyboard
32GB Internal NAND Android 5.0 7" 1920X1200 103% sRGB & 572 cd/m2 LTPS IPS Microsoft Wedge Mobile Keyboard 
PowerAudio
3950mAh/15.01mAh Battery Stereo Speakers 
  hide details  
Reply
The Machine
(14 items)
 
Nexus 7 2013
(11 items)
 
 
CPUMotherboardGraphicsRAM
A10 6800K Asus F2A85-V MSI 6870 Hawx, VTX3D 5770, AMD HD6950(RIP), Sap... G.skill Ripjaws PC12800 6-8-6-24 
Hard DriveOptical DriveOSMonitor
Seagate 7200.5 1TB NEC 3540 Dvd-Rom Windows 7 x32 Ultimate Samsung P2350 23" 1080p 
PowerCaseMouseAudio
Seasonic s12-600w CoolerMaster Centurion 5 Logitech G600 Auzen X-Fi Raider 
CPUMotherboardGraphicsRAM
Quad Krait 300 at 1.5Ghz Qualcomm APQ8064-1AA SOC Adreno 320 at 400mhz 2GB DDR3L-1600 
Hard DriveOSMonitorKeyboard
32GB Internal NAND Android 5.0 7" 1920X1200 103% sRGB & 572 cd/m2 LTPS IPS Microsoft Wedge Mobile Keyboard 
PowerAudio
3950mAh/15.01mAh Battery Stereo Speakers 
  hide details  
Reply
post #57 of 724
Quote:
Originally Posted by DrFPS View Post

You must be kind'a of new as to how the gpu industry works? It's called a paper launch. Yes it is a launch.

The product is not ready for market, yet the manufacture wants to show it off. They all do it.
IMHO nvidia could care less about amd. Nvidia has 82% market share why would they care. Case and point look at any, ANY gpu benchmark.
Its so dominated, amd has giving up on benchmarks. I can't remember a time in gpu history when performance and efficiency was so lopsided, ever. Don't get me wrong. If I could push a magic button, or had a secret bank account.

I would do anything I could to fix this. Fact is we are all going to suffer. It won't matter who's gpu you have in your computer, prices are going up. We need to all get behind amd and cheer them on, they need a break. I hope they have one coming.

However if you look at amd stock closing price @ $2.00USD. They have no cash flow at all, none. So as a result you have $0.00 for research and development. The benchmarks, the lack of performance in the games all show this.

When your broke your broke. AMD is just that! I don't care who you are. YOu have to know that this is really bad for all us consumers sad-smiley-002.gif
http://wccftech.com/amd-regaining-gpu-market-share-nvidia/

GPU benchmarks as in Firestrike? Because if it's for the games themselves, nvidia has a lot of reasons to be concerned, no wonder they had to pull maxwell ahead and insert pascal in their gpu roadmap and have gamesworks show up in so many of the new titles.



AMD's bigger problem is their CPU division and the perception that they're behind in GPU division.
    
CPUMotherboardGraphicsRAM
e2140@3.2Ghz abit IP35-E HIS IceQ4 4850 4GB 667@800 5-5-5-15 
OSPower
win xp 32 bit Corsair 450VX@stock 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
e2140@3.2Ghz abit IP35-E HIS IceQ4 4850 4GB 667@800 5-5-5-15 
OSPower
win xp 32 bit Corsair 450VX@stock 
  hide details  
Reply
post #58 of 724
If AMD completely fixed their DX11 CPU overhead issue, I think their cards should at least be on parity with nVidia's offerings at every resolution and price point.
post #59 of 724
I'd call it multithreading issue, for CPU overhead for AMD drivers is most probably less than nvidia's since they have hardware scheduling.Fury X is mostly easier on CPU than 980Ti in these comparisons.

https://www.youtube.com/user/DudeRandom84/videos

And then there is front end 'issue' with AMD cards.
    
CPUMotherboardGraphicsRAM
e2140@3.2Ghz abit IP35-E HIS IceQ4 4850 4GB 667@800 5-5-5-15 
OSPower
win xp 32 bit Corsair 450VX@stock 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
e2140@3.2Ghz abit IP35-E HIS IceQ4 4850 4GB 667@800 5-5-5-15 
OSPower
win xp 32 bit Corsair 450VX@stock 
  hide details  
Reply
post #60 of 724
Quote:
Originally Posted by DNMock View Post

This isn't news...

HBM2 GPU's won't show up until the Q3, this has been known for quite some time. This does not mean that Pascal and Polaris GPU's won't show up before then as the mid grade cards (R9 490, GTX 1080, etc.) won't be using HBM2, but GDDR5X. Those cards will release in the next month or two. Then around Q3, the 1080ti, Titan P (still going with that as it's title), and the successor to the Fury and Fury X all sporting HBM2 will arrive.

I would expect the Titan P to be the first to show up around computex, followed shortly by the AMD cards and finally the 1080ti showing up in time for the holidays.

Bingo

H2 2016 is about HBM2 cards. It takes time to get enough of HBM2 since mass production just recently started
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Rumors and Unconfirmed Articles
Overclock.net › Forums › Industry News › Rumors and Unconfirmed Articles › [TT] NVIDIA should launch its next-gen Pascal GPUs with HBM2 in 2H 2016